Merge pull request #6 from internetofwater/addOntologyLoaderContainer

Add Loader Container for Ontologies

Author: C-Loftus

.github/workflows/push_loader_image.yml

@@ -0,0 +1,43 @@
+# Copyright 2025 Lincoln Institute of Land Policy
+# SPDX-License-Identifier: Apache-2.0
+
+name: Push Loader Image To GHCR
+
+on:
+  push:
+    branches: [main]
+  workflow_dispatch:
+
+concurrency:
+  group:
+    ${{ github.workflow }}-${{ github.ref_name }}-${{
+    github.event.pull_request.number || github.sha }}
+  cancel-in-progress: true
+
+jobs:
+  build_and_push:
+    name: "build and push geoconnex ontology loader image"
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+
+      - name: Set up Docker Buildx
+        uses: docker/setup-buildx-action@v3
+
+      - name: Login to GitHub Container Registry
+        uses: docker/login-action@v3
+        with:
+          registry: ghcr.io
+          username: ${{ github.actor }}
+          password: ${{ secrets.GITHUB_TOKEN }}
+
+      - name: Build and export
+        uses: docker/build-push-action@v6
+        with:
+          context: .
+          file: Dockerfile
+          push: true
+          tags: ghcr.io/internetofwater/geoconnex_ontology_loader:latest
+          cache-from: type=gha,scope=geoconnex_ontology_loader
+          platforms: linux/amd64
+          cache-to: type=gha,mode=max,scope=geoconnex_ontology_loader

.gitignore

@@ -0,0 +1 @@
+.venv

Dockerfile

@@ -0,0 +1,27 @@
+# Copyright 2026 Lincoln Institute of Land Policy
+# SPDX-License-Identifier: MIT
+
+FROM ghcr.io/astral-sh/uv:python3.12-bookworm-slim
+
+WORKDIR /app
+
+ENV UV_COMPILE_BYTECODE=1
+ENV UV_LINK_MODE=copy
+ENV UV_NO_DEV=1
+
+COPY ./loader/pyproject.toml ./loader/uv.lock ./
+
+RUN --mount=type=cache,target=/root/.cache/uv \
+    uv sync --locked --no-install-project
+
+COPY ./loader/ ./
+COPY ./*.ttl ./
+
+RUN --mount=type=cache,target=/root/.cache/uv \
+    uv sync --locked
+
+ENV PATH="/app/.venv/bin:$PATH"
+
+ENTRYPOINT []
+
+CMD ["python", "/app/main.py"]

loader/.python-version

@@ -0,0 +1 @@
+3.12

loader/README.md

@@ -0,0 +1,35 @@
+import json
+from pathlib import Path
+
+from rdflib import Graph
+
+# trivial script to convert ttl to json-ld and write it to stdout
+# so that the geoconnex pipeline can consume it like a normal integration
+
+def main():
+    current_dir = Path(__file__).parent
+
+    ttl_files = list(current_dir.glob("*.ttl"))
+    if not ttl_files:
+        raise Exception(f"No ttl files found in {current_dir}")
+
+    for ttl_file in ttl_files:
+        graph = Graph()
+        graph.parse(ttl_file, format="turtle")
+
+        # Serialize to JSON-LD
+        jsonld = graph.serialize(format="json-ld")
+
+        # Re-encode as compact one-line JSON 
+        # this is since rdflib doesn't support writing compact JSON
+        # as far as I can tell
+        compact = json.dumps(
+            json.loads(jsonld),
+            separators=(",", ":"),
+        )
+
+        print(compact)
+
+
+if __name__ == "__main__":
+    main()

loader/main.py

@@ -0,0 +1,9 @@
+[project]
+name = "loader"
+version = "0.1.0"
+description = "Add your description here"
+readme = "README.md"
+requires-python = ">=3.12"
+dependencies = [
+    "rdflib>=7.6.0",
+]